Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ные
    -0.06
    들이
    -0.06
     modificar
    -0.06
     Các
    -0.06
    щ
    -0.06
    ูต
    -0.06
     Attendance
    -0.06
     technology
    -0.06
    린
    -0.06
     thép
    -0.06
    POSITIVE LOGITS
     ;;
    0.07
    registered
    0.07
    ..........
    0.06
     (^
    0.06
     BG
    0.06
    ^(
    0.06
    sit
    0.06
     तब
    0.06
     nhiên
    0.06
     Gl
    0.06
    Act Density 0.035%

    No Known Activations